vidtheque.

read-only demo

Videos pmoDeA3RBZY

Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff — Vincent Koc, OpenClaw

index_state ready data_status ok

AI Engineer· published 2026-06-05· 0:16:44· en· indexed 2026-08-10 19:57

Open on YouTube

Scene timeline

  1. Shot 0, 0:00 to 0:05, 1 of 1 keyframes kept
  2. Shot 1, 0:05 to 0:09, 1 of 1 keyframes kept
  3. Shot 2, 0:09 to 0:14, 1 of 1 keyframes kept
  4. Shot 3, 0:14 to 0:20, 1 of 1 keyframes kept
  5. Shot 4, 0:20 to 0:40, 1 of 1 keyframes kept
  6. Shot 5, 0:40 to 1:02, 1 of 1 keyframes kept
  7. Shot 6, 1:02 to 1:04, 1 of 1 keyframes kept
  8. Shot 7, 1:04 to 1:08, 1 of 1 keyframes kept
  9. Shot 8, 1:08 to 1:18, 1 of 1 keyframes kept
  10. Shot 9, 1:18 to 1:27, 1 of 1 keyframes kept
  11. Shot 10, 1:27 to 1:33, 1 of 1 keyframes kept
  12. Shot 11, 1:33 to 1:52, 1 of 1 keyframes kept
  13. Shot 12, 1:52 to 2:17, 0 of 1 keyframes kept
  14. Shot 13, 2:17 to 2:26, 1 of 1 keyframes kept
  15. Shot 14, 2:26 to 2:35, 1 of 1 keyframes kept
  16. Shot 15, 2:35 to 2:51, 1 of 1 keyframes kept
  17. Shot 16, 2:51 to 3:07, 1 of 1 keyframes kept
  18. Shot 17, 3:07 to 3:26, 1 of 1 keyframes kept
  19. Shot 18, 3:26 to 4:02, 1 of 1 keyframes kept
  20. Shot 19, 4:02 to 4:38, 1 of 1 keyframes kept
  21. Shot 20, 4:38 to 4:45, 1 of 1 keyframes kept
  22. Shot 21, 4:45 to 4:47, 1 of 1 keyframes kept
  23. Shot 22, 4:47 to 5:11, 1 of 1 keyframes kept
  24. Shot 23, 5:11 to 5:19, 1 of 1 keyframes kept
  25. Shot 24, 5:19 to 5:26, 1 of 1 keyframes kept
  26. Shot 25, 5:26 to 5:42, 1 of 1 keyframes kept
  27. Shot 26, 5:42 to 5:49, 1 of 1 keyframes kept
  28. Shot 27, 5:49 to 6:11, 1 of 1 keyframes kept
  29. Shot 28, 6:11 to 6:29, 1 of 1 keyframes kept
  30. Shot 29, 6:29 to 6:40, 1 of 1 keyframes kept
  31. Shot 30, 6:40 to 7:13, 1 of 1 keyframes kept
  32. Shot 31, 7:13 to 7:25, 1 of 1 keyframes kept
  33. Shot 32, 7:25 to 7:32, 1 of 1 keyframes kept
  34. Shot 33, 7:32 to 7:44, 1 of 1 keyframes kept
  35. Shot 34, 7:44 to 7:55, 1 of 1 keyframes kept
  36. Shot 35, 7:55 to 8:24, 1 of 1 keyframes kept
  37. Shot 36, 8:24 to 8:52, 1 of 1 keyframes kept
  38. Shot 37, 8:52 to 9:21, 1 of 1 keyframes kept
  39. Shot 38, 9:21 to 9:44, 1 of 1 keyframes kept
  40. Shot 39, 9:44 to 9:55, 1 of 1 keyframes kept
  41. Shot 40, 9:55 to 10:29, 0 of 1 keyframes kept
  42. Shot 41, 10:29 to 11:03, 1 of 1 keyframes kept
  43. Shot 42, 11:03 to 11:12, 1 of 1 keyframes kept
  44. Shot 43, 11:12 to 11:49, 1 of 1 keyframes kept
  45. Shot 44, 11:49 to 11:57, 1 of 1 keyframes kept
  46. Shot 45, 11:57 to 12:04, 1 of 1 keyframes kept
  47. Shot 46, 12:04 to 12:17, 1 of 1 keyframes kept
  48. Shot 47, 12:17 to 12:48, 1 of 1 keyframes kept
  49. Shot 48, 12:48 to 13:19, 1 of 1 keyframes kept
  50. Shot 49, 13:19 to 13:24, 1 of 1 keyframes kept
  51. Shot 50, 13:24 to 13:31, 1 of 1 keyframes kept
  52. Shot 51, 13:31 to 14:01, 1 of 1 keyframes kept
  53. Shot 52, 14:01 to 14:23, 1 of 1 keyframes kept
  54. Shot 53, 14:23 to 14:45, 1 of 1 keyframes kept
  55. Shot 54, 14:45 to 14:56, 1 of 1 keyframes kept
  56. Shot 55, 14:56 to 15:20, 1 of 1 keyframes kept
  57. Shot 56, 15:20 to 15:26, 1 of 1 keyframes kept
  58. Shot 57, 15:26 to 15:35, 1 of 1 keyframes kept
  59. Shot 58, 15:35 to 16:02, 1 of 1 keyframes kept
  60. Shot 59, 16:02 to 16:29, 1 of 1 keyframes kept
  61. Shot 60, 16:29 to 16:43, 1 of 1 keyframes kept

61 shot(s).

keyframes kept every frame deduplicated

What was stored

cues
257
whisperx 257
chunks
30
from 257 cues
keyframes
59
kept of 61 captured
frames with text
59
1,079 lines read
chapters
0
from the source metadata
keyframe bytes
7.9 MB
word timings on 257 cues

Provenance

Each pipeline stage, its state and the model that produced it
stage state model started took
fetch done — 2026-08-10 19:26 2m 19s
stt done — 2026-08-10 19:28 19s
chunk done — 2026-08-10 19:29 0s
text_embed done — 2026-08-10 19:56 1s
keyframe done — 2026-08-10 19:29 1m 40s
ocr done — 2026-08-10 19:30 17s
frame_embed done — 2026-08-10 19:56 9s

Frames, and what the machine read

  • 0:02 #0 done2 line(s)

    shot 0·sharpness 667.3

    1. Al Engineer0.94
    2. EUROPE1.00

  • 0:06 #1 done2 line(s)

    shot 1·sharpness 825.0

    1. PRESENTINGSPONSOR1.00
    2. Google DeepMind1.00

  • 0:11 #2 done3 line(s)

    shot 2·sharpness 938.6

    1. PLATINUM SPONSORS0.98
    2. # Braintrust0.95
    3. WorkOS OpenAI0.95

  • 0:19 #3 done16 line(s)

    shot 3·sharpness 1952.1

    1. Braintrust1.00
    2. AlEng0.98
    3. EURO0.99
    4. AlEngin0.99
    5. sner0.84
    6. EU0.64
    7. Eng1.00
    8. Dark Factories: OpenClaw Ships0.99
    9. EURO0.99
    10. Faster Than You Can Read the Diff0.98
    11. AIE0.96
    12. Vincent Koc (@vincent_koc)1.00
    13. OpenClaw1.00
    14. Google DeepMind1.00
    15. AlEngineer0.98
    16. EUROPE1.00

  • 0:30 #4 done23 line(s)

    shot 4·sharpness 1921.6

    1. Engineer1.00
    2. EUROPE1.00
    3. ogetherai1.00
    4. Engineer1.00
    5. ROPE1.00
    6. Engineer1.00
    7. 040.99
    8. EUROPE1.00
    9. arize1.00
    10. Engineer1.00
    11. Dark Factories: OpenClaw Ships0.98
    12. EUROPE1.00
    13. Faster Than You Can Read the Diff1.00
    14. Engineer1.00
    15. :ailsca1.00
    16. EUROPE1.00
    17. Vincent Koc (@vincent_koc)1.00
    18. OpenClaw1.00
    19. AlEngineer0.99
    20. # Braintrust0.95
    21. WorkOS1.00
    22. OpenAl0.95
    23. EUROPE1.00

  • 0:44 #5 done21 line(s)

    shot 5·sharpness 1478.1

    1. AlEngineer0.98
    2. EUROPE1.00
    3. I wake up1.00
    4. togeth0.98
    5. AlEngi0.95
    6. EUROI0.88
    7. AIE1.00
    8. ned0.80
    9. al0.80
    10. AlEngi0.93
    11. EURO1.00
    12. AlEng0.91
    13. tail1.00
    14. EURO1.00
    15. there is a new1.00
    16. technological advancement0.98
    17. Vincent Koc1.00
    18. AIE Europe 20261.00
    19. Engineering the future of Al1.00
    20. AlEngineer0.98
    21. EUROPE1.00

  • 1:04 #6 done12 line(s)

    shot 6·sharpness 1456.9

    1. ngineer1.00
    2. Braintru0.99
    3. I wake up1.00
    4. enA0.97
    5. there is a new1.00
    6. EI0.91
    7. technological advancement0.98
    8. Vincent Koc0.96
    9. AIE Europe 20261.00
    10. Google DeepMind0.99
    11. AlEngineer0.99
    12. EUROPE1.00

  • 1:05 #7 done13 line(s)

    shot 7·sharpness 980.1

    1. AlEngineer0.96
    2. Bra1.00
    3. EUROPE1.00
    4. Hi I'm Vincent Koc1.00
    5. Your Friendly Clanker1.00
    6. Open1.00
    7. AIEn0.88
    8. S0.56
    9. Vincent Koc1.00
    10. AIE Europe 20261.00
    11. Google DeepMind1.00
    12. AlEngineer0.98
    13. EUROPE1.00

  • 1:14 #8 done21 line(s)

    shot 8·sharpness 1471.2

    1. raintrust1.00
    2. AlEngineer0.98
    3. EUROPE0.98
    4. Hi I'm Vincent Koc1.00
    5. Your Friendly Clanker1.00
    6. 04j0.99
    7. Engineer1.00
    8. EUROPE1.00
    9. My love for testing new1.00
    10. technology (2013)1.00
    11. Snor1.00
    12. igineer0.97
    13. ROPE1.00
    14. Engine1.00
    15. SS0.93
    16. EUROPE1.00
    17. Vincent Koc1.00
    18. AIE Europe 20260.99
    19. Google DeepMind1.00
    20. AlEngineer0.98
    21. EUROPE1.00

  • 1:20 #9 done18 line(s)

    shot 9·sharpness 1434.0

    1. EUROPE0.94
    2. Hi I'm Vincent Koc1.00
    3. Your Friendly Clanker1.00
    4. ngineer1.00
    5. EUROPE0.99
    6. My love for testing new1.00
    7. AlEngineer0.99
    8. technology (2013)0.96
    9. EUROPE1.00
    10. Braintrus1.00
    11. ailsc0.98
    12. AlEngineer0.98
    13. EUROPE1.00
    14. Vincent Koc1.00
    15. AIE Europe 20260.99
    16. Google DeepMind1.00
    17. AlEngineer0.98
    18. EUROPE1.00

  • 1:27 #10 done13 line(s)

    shot 10·sharpness 1506.5

    1. Hi I'm Vincent Koc1.00
    2. Zed0.82
    3. Your Friendly Clanker1.00
    4. My love for testing new1.00
    5. technology (2013)0.97
    6. arize1.00
    7. Vincent Koc0.97
    8. AIE Europe 20261.00
    9. AlEngineer0.98
    10. # Braintrust0.98
    11. WorkOS1.00
    12. OpenAl0.96
    13. EUROPE0.99

  • 1:39 #11 done22 line(s)

    shot 11·sharpness 1395.1

    1. raintrust0.97
    2. AlEngineer0.98
    3. EUROPE0.99
    4. Hi I'm Vincent Koc1.00
    5. Your Friendly Clanker1.00
    6. neo4j0.94
    7. Engineer0.96
    8. EUROPF0.99
    9. My love for testing new1.00
    10. technology (2013)0.95
    11. Sn1.00
    12. Engin0.90
    13. ess1.00
    14. EUROPE1.00
    15. Vincent Koc1.00
    16. Son0.84
    17. AIE Europe 20261.00
    18. # Braintrust0.98
    19. OpenAl0.94
    20. AlEngineer0.99
    21. WorkOS1.00
    22. EUROPE1.00

  • 2:12 #12 skipped

    shot 12·duplicate of #9

  • 2:19 #13 done15 line(s)

    shot 13·sharpness 9771.2

    1. EUR0.86
    2. AlEngine0.98
    3. Brai1.00
    4. EURO1.00
    5. Ope1.00
    6. AIEng0.91
    7. EURO1.00
    8. AlEng0.96
    9. Mic0.98
    10. EUROP1.00
    11. AIEng0.93
    12. EURO1.00
    13. Google DeepMind1.00
    14. AlEngineer0.99
    15. EUROPE1.00

  • 2:27 #14 done15 line(s)

    shot 14·sharpness 9828.8

    1. WorkOs0.97
    2. AlEngineer0.99
    3. AlEngineer0.95
    4. Braintrust1.00
    5. Tessl1.00
    6. AlEngineer1.00
    7. Snorkel0.99
    8. arize1.00
    9. AlEngineer1.00
    10. AEngin0.99
    11. AlEngineer0.97
    12. # Braintrust0.98
    13. WorkOS1.00
    14. OpenAl0.94
    15. EUROPE1.00

  • 2:37 #15 done10 line(s)

    shot 15·sharpness 9672.1

    1. EUROPE0.99
    2. trust0.99
    3. oft1.00
    4. al1.00
    5. EUR1.00
    6. AIEngineer0.95
    7. # Braintrust0.98
    8. WorkOS1.00
    9. OpenAl0.93
    10. EUROPE1.00

  • 2:53 #16 done10 line(s)

    shot 16·sharpness 9637.0

    1. ineer1.00
    2. OnenAl0.97
    3. OPE0.96
    4. orkOS0.94
    5. jineer0.92
    6. OPE1.00
    7. rize1.00
    8. Engineering the future of Al1.00
    9. AlEngineer0.98
    10. EUROPE1.00

  • 3:17 #17 done18 line(s)

    shot 17·sharpness 1768.4

    1. AlEngineer1.00
    2. OpenAl0.98
    3. EUROPE1.00
    4. WorkOs0.93
    5. AlEng.or0.82
    6. Hand Looms In Cottages1.00
    7. EUROPE1.00
    8. Centralized Large Mills1.00
    9. Craftsmen are Factory Workers1.00
    10. arize1.00
    11. Bottleneck: The weavers' hands0.98
    12. AlEngineer0.99
    13. EUROPE1.00
    14. Vincent Koc1.00
    15. AIE Europe 20261.00
    16. Google DeepMind1.00
    17. AlEngineer0.98
    18. EUROPE1.00

  • 3:31 #18 done25 line(s)

    shot 18·sharpness 1820.1

    1. ineer0.96
    2. PE1.00
    3. o4j0.98
    4. AIEngineer0.95
    5. UROPE1.00
    6. nAl0.96
    7. ineer1.00
    8. PE1.00
    9. Engineers Writing Code in Editors1.00
    10. Agent Swarms on Repos1.00
    11. NTRY1.00
    12. Engineer1.00
    13. Engineers are Factory Managers0.99
    14. EUROPE1.00
    15. Bottleneck: Engineers Taste1.00
    16. ineer1.00
    17. Modal1.00
    18. PE0.99
    19. Vincent Koc1.00
    20. AIE Europe 20260.96
    21. AlEngineer0.98
    22. # Braintrust0.97
    23. WorkOS1.00
    24. OpenAl0.94
    25. EUROPE1.00

  • 4:34 #19 done24 line(s)

    shot 19·sharpness 2613.0

    1. EUROP0.94
    2. Engineer1.00
    3. OpenA1.00
    4. EUROPE1.00
    5. le Der0.85
    6. 1Engineer0.98
    7. EUROPE1.00
    8. Anthropic: 16 parallel Claudes. 100K-line C compiler (2wks)1.00
    9. Spotify: 650 AI PR's/m. No Hand Code Since Dec 250.99
    10. Engin1.00
    11. Braintr1.00
    12. Yegge: 50 PRs/day. Solo. Vibe Maintainer1.00
    13. EUROPE1.00
    14. OpenClaw: 800 commits/day peak0.99
    15. eNCOR.0.91
    16. AIEngineer0.94
    17. EUROPE1.00
    18. Vincent Koc0.96
    19. AIE Europe 20260.99
    20. AIEngineer0.95
    21. #Braintrust0.98
    22. WorkOS1.00
    23. OpenAl0.94
    24. EUROPE1.00

  • 4:44 #20 done11 line(s)

    shot 20·sharpness 2561.2

    1. Microso0.99
    2. AlEngineer0.93
    3. Anthropic: 16 parallel Claudes. 100K-line C compiler (2wks)0.98
    4. Spotify: 650 AI PR's/m. No Hand Code Since Dec 250.99
    5. Yegge: 50 PRs/day. Solo. Vibe Maintainer1.00
    6. OpenClaw: 800 commits/day peak0.98
    7. Vincent Koc0.99
    8. AIE Europe 20261.00
    9. Engineering the future of Al0.99
    10. AlEngineer0.98
    11. EUROPE1.00

  • 4:45 #21 done17 line(s)

    shot 21·sharpness 2631.7

    1. oogleDeepiind0.85
    2. AlEngir0.85
    3. ATrigger.de0.95
    4. AlEngineer1.00
    5. Anthropic: 16 parallel Claudes. 100K-line C compiler (2wks)0.98
    6. EUROPE1.00
    7. Spotify: 650 AI PR's/m. No Hand Code Since Dec 250.99
    8. comet0.99
    9. Yegge: 50 PRs/day. Solo. Vibe Maintainer1.00
    10. OpenClaw: 800 commits/day peak0.99
    11. AlEngineer0.98
    12. EUROPE0.97
    13. Vincent Koc1.00
    14. AIE Europe 20260.97
    15. Engineering the future of Al1.00
    16. AlEngineer0.98
    17. EUROPE1.00

  • 5:08 #22 done26 line(s)

    shot 22·sharpness 1183.2

    1. Google DeepMind0.98
    2. AlEngined0.94
    3. EUROPE0.85
    4. Trigger.0.95
    5. AlEnn0.82
    6. Contribution settings1.00
    7. 20261.00
    8. 2886 contributions on March 15th.0.98
    9. Enginee1.00
    10. Dec1.00
    11. Jan1.00
    12. 20251.00
    13. EUROPE0.97
    14. 20241.00
    15. com1.00
    16. 20231.00
    17. Less1.00
    18. ●More0.92
    19. 20221.00
    20. AlEnginer0.99
    21. 20?10.60
    22. Vincent Koc1.00
    23. AIE Europe 20260.99
    24. Google DeepMind1.00
    25. AlEngineer0.97
    26. EUROPE1.00

  • 5:16 #23 done21 line(s)

    shot 23·sharpness 1131.8

    1. AlEngl0.83
    2. Unblocke1.00
    3. Contribution settings1.00
    4. 20261.00
    5. AlEngl0.80
    6. Dec1.00
    7. Jan1.00
    8. 2886 contributions on March 15th.1.00
    9. 20251.00
    10. 20241.00
    11. 20231.00
    12. AlEng0.98
    13. Less1.00
    14. More1.00
    15. 20221.00
    16. 20210.83
    17. Vincent Koc1.00
    18. AIE Europe 20260.99
    19. Google DeepMind0.99
    20. AlEngineer0.97
    21. EUROPE1.00

Transcript

257 cues· 3,097 words· 16,189 chars

  1. 0:15 They've got it?
  2. 0:16 Cool.
  3. 0:16 Amazing.
  4. 0:17 So welcome everyone.
  5. 0:18 I'm Vincent.
  6. 0:20 What do I do?
  7. 0:21 I'm one of the core maintainers at OpenClaw working with Peter.
  8. 0:25 As you've heard before, I have a day job as well.
  9. 0:28 Same as Peter, he has a day job at OpenAI.
  10. 0:31 But it's an open source project, amazing things have been happening.
  11. 0:34 I'm going to talk about what I call dark factories and how OpenClaw ships faster than you can read the diff.
  12. 0:41 This meme is absolutely hilarious.
  13. 0:42 So I think Peter posted this a week or two ago.
  14. 0:45 I wake up, there's a new technological advancement, I wake up.
  15. 0:49 It's this joke that we're shipping at insane speed and the velocity is just absolutely phenomenal.
  16. 0:55 And some of you might think, oh, this is some luck or we're just like Ralph looping to the max.
  17. 1:02 I think there's actual engineering work here and I'm gonna talk about that.
  18. 1:05 Now, as I mentioned, I'm Vincent.
  19. 1:07 I'm your friendly clanker.
  20. 1:10 This is me using VR goggles back in 2013.
  21. 1:12 So despite my accent that sounds somewhat Australian, I was born and raised in East London, not far from here.
  22. 1:17 I actually went to college just down the road in Westminster.
  23. 1:20 And yeah, at some point decided to live in Australia and my accent changed.
  24. 1:23 But I used to love technology.
  25. 1:25 I used to love being at the edge of technology.
  26. 1:28 And this was like one of the first few sort of early VR goggles that came out.
  27. 1:32 It came in this big box with a big warning sign on it saying, hey,
  28. 1:36 used for five minutes at a time, because it didn't have the anti-motion sickness built into it.
  29. 1:40 And the funny thing with this one here was that I didn't use it for five minutes, I used it for three hours.
  30. 1:46 And I played Team Fortress 2, had an absolute blast, and then I vomited for three hours after that, because my vision turned into B vision.
  31. 1:54 What I'm trying to say here is that anything on the edge is gonna be janky, it's gonna be
  32. 1:59 horrific, it's going to be uncharted territory.
  33. 2:04 And working on OpenClaw and being part of the team that ships probably, you know, an insane velocity of commits to a point where I get rate limited by GitHub on an hourly basis is an interesting experience.
  34. 2:18 And this experience Britain's gone through before.
  35. 2:22 We had the industrial revolution when
  36. 2:24 mills and cotton were being produced at extreme amounts of volume.
  37. 2:29 And there's a lot of history here around production and productionization at scale in the UK and in Europe.
  38. 2:36 And I feel like we're going through this moment again, we're going through this moment of how do we build at scale, and the ways we used to work before just don't work anymore.
  39. 2:46 And
  40. 2:48 It's kind of strange, because in my day job, I kind of work in the space of evals, which everything is sort of structured, and there's telemetry, and it has to be all perfect.
  41. 2:58 And I work on a project where I have this blind faith in the harness.
  42. 3:04 And it's this kind of two walls.
  43. 3:05 But they're starting to come together.
  44. 3:08 We used to have hand looms in cottages, centralized mills everywhere.
  45. 3:14 Craftsmen were the factory workers.
  46. 3:17 But the bottleneck was the weaver's hands.
  47. 3:20 We're now switching to a world where engineers writing code and editors, not so much.
  48. 3:25 Swarms across repos.
  49. 3:28 Engineers are becoming factory managers, which I'm going to talk to.
  50. 3:32 And the bottleneck becomes taste.

Open at this second